Human‐multimodal deep learning collaboration in ‘precise’ diagnosis of lupus erythematosus subtypes and similar skin diseases
Journal of the European Academy of Dermatology and Venereology · 2024-12 · 38 (12) · 2268-2279
DOI: 10.1111/jdv.20031 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Journal of the European Academy of Dermatology and Venereology, 2024-12. Verfasst von Qianwen Li und 59 weiteren Autor:innen. Beteiligte Einrichtung: Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China. Hauptthemen laut MEDLINE: Deep Learning, Lupus Erythematosus, Cutaneous. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: Key Research and Development Program of Hunan Province, China, Clinical Medical Innovation Guide Project of Hunan Province, Hunan Talent Young Investigator of China.
Abstract (Originalsprache)
Background
Lupus erythematosus (LE) is a spectrum of autoimmune diseases. Due to the complexity of cutaneous LE (CLE), clinical skin image‐based artificial intelligence is still experiencing difficulties in distinguishing subtypes of LE.
Objectives
We aim to develop a multimodal deep learning system (MMDLS) for human‐AI collaboration in diagnosis of LE subtypes.
Methods
This is a multi‐centre study based on 25 institutions across China to assist in diagnosis of LE subtypes, other eight similar skin diseases and healthy subjects. In total, 446 cases with 800 clinical skin images, 3786 multicolor‐immunohistochemistry (multi‐IHC) images and clinical data were collected, and EfficientNet‐B3 and ResNet‐18 were utilized in this study.
Results
In the multi‐classification task, the overall performance of MMDLS on 13 skin conditions is much higher than single or dual modals (Sen = 0.8288, Spe = 0.9852, Pre = 0.8518, AUC = 0.9844). Further, the MMDLS‐based diagnostic‐support help improves the accuracy of dermatologists from 66.88% ± 6.94% to 81.25% ± 4.23% ( p = 0.0004).
Conclusions
These results highlight the benefit of human‐MMDLS collaborated framework in telemedicine by assisting dermatologists and rheumatologists in the differential diagnosis of LE subtypes and similar skin diseases.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
- Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education, Xiangtan University, Xiangtan, China.
- Department of Dermatology, Hunan Children's Hospital, Changsha, China.
- Institute of Dermatology, Chinese Academy of Medical Sciences and Peking Union Medical College, Nanjing, China.
- Department of Dermatology, Beijing Chao-Yang Hospital, Capital Medical University, Beijing, China.
- Department of Dermatology, Peking University Third Hospital, Beijing, China.
ORCID-Profile: Kaili Chen, Hai Long, Guishao Tang, Xiaojing Kang, Hongzhong Jin, Jianyun Lu, Jinrong Zeng, Xian Jiang, Bin Hu, Juan Tao, Zhirong Yao, Qianyue Xu
Förderung
- Key Research and Development Program of Hunan Province, China
- Clinical Medical Innovation Guide Project of Hunan Province
- Hunan Talent Young Investigator of China
- Nonprofit Central Research Institute Fund of the Chinese Academy of Medical Sciences
- Hunan Outstanding Young Investigator of China
- National Natural Science Foundation of China
- CAMS Innovation Fund for Medical Sciences (CIFMS)
- National Key R&D Program of China
Zitieren
APA
Li, Q., Yang, Z., Chen, K., Zhao, M., Long, H., Deng, Y., Hu, H., Jia, C., Wu, M., Zhao, Z., Zhu, H., Zhou, S., Zhao, M., Cao, P., Zhou, S., Song, Y., Tang, G., Liu, J., Jiang, J., …, & Xu, Q. (2024). Human‐multimodal deep learning collaboration in ‘precise’ diagnosis of lupus erythematosus subtypes and similar skin diseases. Journal of the European Academy of Dermatology and Venereology. https://doi.org/10.1111/jdv.20031
Vancouver
Li Q, Yang Z, Chen K, Zhao M, Long H, Deng Y, et al. Human‐multimodal deep learning collaboration in ‘precise’ diagnosis of lupus erythematosus subtypes and similar skin diseases. Journal of the European Academy of Dermatology and Venereology. 2024. doi:10.1111/jdv.20031
BibTeX
@article{Li2024,
author = {Li, Qianwen and Yang, Zhi and Chen, Kaili and Zhao, Ming and Long, Hai and Deng, Yueming and Hu, Haoran and Jia, Chen and Wu, Meiyu and Zhao, Zhidan and Zhu, Huan and Zhou, Suqing and Zhao, Mingming and Cao, Pengpeng and Zhou, Shengnan and Song, Yang and Tang, Guishao and Liu, Juan and Jiang, Jiao and Liao, Wei and Zhou, Wenhui and Yang, Bingyi and Xiong, Feng and Zhang, Suhan and Gao, Xiaofei and Jiang, Yiqun and Zhang, Wei and Zhang, Bo and He, Yan-Ling and Ran, Liwei and Zhang, Chunlei and Wu, Wenting and Suolang, Quzong and Luo, Hanhuan and Kang, Xiaojing and Wu, Caoying and Jin, Hongzhong and Chen, Lei and Guo, Qing and Gui, Guangji and Li, Shanshan and Si, Henan and Guo, Shuping and Liu, Hong-Ye and Liu, Xiguang and Ma, Guo-Zhang and Deng, Danqi and Yuan, Limei and Lu, Jianyun and Zeng, Jinrong and Jiang, Xian and Lyu, Xiaoyan and Chen, Liuqing and Hu, Bin and Tao, Juan and Liu, Yuhao and Wang, Gang and Zhu, Guannan and Yao, Zhirong and Xu, Qianyue},
title = {Human‐multimodal deep learning collaboration in ‘precise’ diagnosis of lupus erythematosus subtypes and similar skin diseases},
journal = {Journal of the European Academy of Dermatology and Venereology},
year = {2024},
doi = {10.1111/jdv.20031}
}
EUVIMED